ask-skills

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command to parse files: python3 -B "$TICKET_AUTOPILOT_ROOT/scripts/ticket-autopilot.py" ticket-parse <ticket.md>. This is part of its core routing logic.
  • [DYNAMIC_EXECUTION]: The execution path for the ticket-parsing script is resolved dynamically at runtime via the $TICKET_AUTOPILOT_ROOT environment variable and a catalog lookup.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Markdown files which can influence downstream agent actions.
  • Ingestion points: The skill reads user-supplied or environment-resident <ticket.md> files.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ticket files are provided in the routing logic.
  • Capability inventory: The skill possesses the ability to execute shell commands (python3) and route parsed data to other 'execution' skills.
  • Sanitization: There is no evidence of sanitization or validation of the ticket content before it is parsed and passed to other execution flows.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 11:24 AM
Security Audit — agent-trust-hub — ask-skills